Zero-shot cross-domain slot filling is becoming increasingly important due to its ability to generalize to new domains without the need for annotating domain-specific data, which aligns well with the requirements of industrial deployments. Recent advanced works deal with this task through question answering framework and make remarkable progress. However, they always rely on human efforts to manually construct question templates or prompts for all slot types, which is not only labor consuming, but also experience context inconsistency issue between the manual example and the specific test instance. To alleviate this problem, we introduce a retriever designed to extract reference samples from the training sets, serving as demonstrations to guide the model in generating the target slot entity through in-context learning. Building upon this retriever, we propose a retrieval-augmented generative framework that automatically constructs and tailors prompts to each specific test instance, eliminating the need for manual efforts. Experiment results verify that our approach attains the state-of-the-art.

Low-resource complex named entity recognition focuses on identifying complex entities such as creative work, product name and so on, in scenarios where annotated training data is limited. Recent advanced works deal with this task through data augmentation and make substantial progress. However, existing methods ignore the influence of different types or levels of augmented data on model optimization in different learning stages. To address it, we propose a dual-perspective data augmentation and curriculum learning framework. Specifically, we first employ the large language model (LLM) to construct two kinds of augmented datasets from context-perspective and entity-perspective, respectively. Then, we present a multi-stage curriculum learning strategy including a novel adaptive curriculum arrangement algorithm to automatically select the most suitable kind of augmented set to optimize the target model at each training epoch, thus using the augmented data more effectively and controllably. Experimental results on the public benchmark across various low-resource settings show that our framework outperforms previous works.

Multi-Modal Entity Alignment (MMEA) aims to retrieve equivalent entities from different Multi-Modal Knowledge Graphs (MMKGs), a critical information retrieval task.Existing studies have explored various fusion paradigms and consistency constraints to improve the alignment of equivalent entities, while overlooking that the visual modality may not always contribute positively.Empirically, entities with low-similarity images usually generate unsatisfactory performance, highlighting the limitation of overly relying on visual features.We believe the model can be biased toward the visual modality, leading to a shortcut image-matching task.To address this, we propose a counterfactual debiasing framework for MMEA, termed CDMEA, which investigates visual modality bias from a causal perspective.Our approach aims to leverage both visual and graph modalities to enhance MMEA while suppressing the direct causal effect of the visual modality on model predictions.By estimating the Total Effect (TE) of both modalities and excluding the Natural Direct Effect (NDE) of the visual modality, we ensure that the model predicts based on the Total Indirect Effect (TIE), * Corresponding author.

Multi-intent detection and slot filling joint model attracts more and more attention since it can handle multi-intent utterances, which is closer to complex real-world scenarios.Most existing joint models rely entirely on the training procedure to obtain the implicit correlation between intents and slots.However, they ignore the fact that leveraging the rich global knowledge in the corpus can determine the intuitive and explicit correlation between intents and slots.In this paper, we aim to make full use of the statistical co-occurrence frequency between intents and slots as prior knowledge to enhance joint multiple intent detection and slot filling.To be specific, an intent-slot cooccurrence graph is constructed based on the entire training corpus to globally discover correlation between intents and slots.Based on the global intent-slot co-occurrence, we propose a novel graph neural network to model the interaction between the two subtasks.Experimental results on two public multi-intent datasets demonstrate that our approach outperforms the state-of-the-art models.

Superconducting (SC) electrodynamic suspension (EDS) has a wide application prospect due to the advantages of no active control, self-stability and large gap, especially in the ultra-high speed maglev, rocket launching, Electromagnetic Aircraft Launching System and other high speed fields. SC coils and null-flux Ground Coils which are the primary and secondary windings respectively are applied in a typical EDS system, in that the null-flux ground coils provide levitation and guidance force. The calculation of electromagnetic forces that has been extensively studied by scholars all over the world is the basis of the design and optimization of the system. However, due to the limitation of complex structure, the calculation formula is often so complicated that the results have to be obtained by means of finite element method and numerical simulation. This paper aims to derive an analytical calculation of electromagnetic forces for SC EDS system based on some reasonable assumptions. The experimental data of MLX01 on the Japanese Yamanashi testline was used to verify the calculation model of this paper. In order to get a further validation, a small EDS rotary table was built based on null-flux ground coils and permanent magnets. The results of the experiment confirms the effectiveness of the proposed analytical calculation model.